Regensburg Pediatric Appendicitis
Linked on 12/6/2023
This repository holds the data from a cohort of pediatric patients with suspected appendicitis admitted with abdominal pain to Children’s Hospital St. Hedwig in Regensburg, Germany, between 2016 and 2021. Each patient has (potentially multiple) ultrasound (US) images, aka views, tabular data comprising laboratory, physical examination, scoring results and ultrasonographic findings extracted manually by the experts, and three target variables, namely, diagnosis, management and severity.
Dataset Characteristics
Tabular, Image
Subject Area
Health and Medicine
Associated Tasks
Classification
Feature Type
Real, Categorical, Integer
# Instances
782
# Features
53
Dataset Information
Additional Information
This dataset was acquired in a retrospective study from a cohort of pediatric patients admitted with abdominal pain to Children’s Hospital St. Hedwig in Regensburg, Germany. Multiple abdominal B-mode ultrasound images were acquired for most patients, with the number of views varying from 1 to 15. The images depict various regions of interest, such as the abdomen’s right lower quadrant, appendix, intestines, lymph nodes and reproductive organs. Alongside multiple US images for each subject, the dataset includes information encompassing laboratory tests, physical examination results, clinical scores, such as Alvarado and pediatric appendicitis scores, and expert-produced ultrasonographic findings. Lastly, the subjects were labeled w.r.t. three target variables: diagnosis (appendicitis vs. no appendicitis), management (surgical vs. conservative) and severity (complicated vs. uncomplicated or no appendicitis). The study was approved by the Ethics Committee of the University of Regensburg (no. 18-1063-101, 18-1063_1-101 and 18-1063_2-101) and was performed following applicable guidelines and regulations.
Has Missing Values?
No
Introductory Paper
By Ricards Marcinkevics, Patricia Reis Wolfertstetter, Ugne Klimiene, Ece Ozkan, Kieran Chin-Cheong, Alyssia Paschke, Julia Zerres, Markus Denzinger, David Niederberger, S. Wellmann, C. Knorr, Julia E. Vogt. 2023
Published in Medical Image Analysis
Variables Table
| Variable Name | Role | Type | Demographic | Description | Units | Missing Values |
|---|---|---|---|---|---|---|
| Age | Feature | Continuous | Age | Obtained from the date of birth | years | yes |
| BMI | Feature | Continuous | Measures body fat; patient's weight divided by the square of the height | yes | ||
| Sex | Feature | Categorical | Sex | Registered gender | yes | |
| Height | Feature | Continuous | Patient's height | yes | ||
| Weight | Feature | Integer | Patient's weight | yes | ||
| Length_of_Stay | Feature | Integer | Length of the stay in the hospital | yes | ||
| Management | Target | Categorical | (conservative, primary surgical, secondary surgical, simultaneous appendectomy) Management of the patient assigned by a senior pediatric surgeon: operative (appendectomy: laparoscopic, open or conversion) or conservative (without antibiotics). In case of the secondary surgery after prior stay, the patient was labelled as operatively managed. | yes | ||
| Severity | Target | Categorical | (uncomplicated, complicated) Severity of appendicitis: uncomplicated: subacute/ catharral, fibrosis; phlegmonous or complicated: gangrenous, perforated, abscessed | yes | ||
| Diagnosis_Presumptive | Other | Binary | Patient's suspected diagnosis | yes | ||
| Diagnosis | Target | Binary | Patient's diagnosis, histologically confirmed for operated patients. Conservatively managed patients were labelled as having appendicitis if they had an AS or PAS of ≥ 4 and an appendix diameter of ≥ 6 mm | yes |
0 to 10 of 58
Additional Variable Information
Class Labels
Diagnosis: [appendicitis, no appendicitis], Severity: [complicated, uncomplicated], Management: [conservative, primary surgical, secondary surgical, simultaneous appendectomy]
Reviews
There are no reviews for this dataset yet.
pip install ucimlrepo
from ucimlrepo import fetch_ucirepo # fetch dataset regensburg_pediatric_appendicitis = fetch_ucirepo(id=938) # data (as pandas dataframes) X = regensburg_pediatric_appendicitis.data.features y = regensburg_pediatric_appendicitis.data.targets # metadata print(regensburg_pediatric_appendicitis.metadata) # variable information print(regensburg_pediatric_appendicitis.variables)
Marcinkevics, R., Reis, P., Klimiene, U., Ozkan, E., Chin-Cheong, K., Paschke, A., Zerres, J., Denzinger, M., Niederberger, D., Wellmann, S., Knorr, C., & E., J. (2023). Regensburg Pediatric Appendicitis [Dataset]. UCI Machine Learning Repository. https://doi.org/10.5281/zenodo.7669442.
Citations/Acknowledgements
If you use this dataset, please follow the acknowledgment policy on the original dataset website.
Keywords
Creators
Ricards Marcinkevics
Patricia Reis
Ugne Klimiene
Ece Ozkan
Kieran Chin-Cheong
Alyssia Paschke
Julia Zerres
Markus Denzinger
David Niederberger
S. Wellmann
C. Knorr
Julia E.